Autonomous Driving Technology Research Articles

The Application and Significance of Autonomous Driving Technology in Industrial Production

In this study, we first gave an overview of autonomous driving technology and focused on its application in industrial production. By analyzing the types and characteristics of autonomous driving technology, we introduced key types such as unmanned vehicles, automated robots, and drones in detail. Subsequently, this paper selected three specific application cases of logistics transportation, warehouse management, and production process automation to deeply analyze the actual application effects of autonomous driving technology in industrial production. In addition, this paper also explores the significance of autonomous driving technology in the industrial production process and its impact on industrial production efficiency and cost. The study found that the application of autonomous driving technology can not only improve production efficiency, but also significantly reduce operating costs. Through this study, we hope to provide theoretical guidance and practical reference for the application of autonomous driving technology in the field of industrial production in my country.

A Mixed Traffic Flow Capacity Vehicle Flow Control Strategy Combining Vehicle Networking Technology and Autonomous Driving Technology

A Mixed Traffic Flow Capacity Vehicle Flow Control Strategy Combining Vehicle Networking Technology and Autonomous Driving Technology

The Impact of Autonomous Driving Technologies on Road Safety and Traffic Management

The Impact of Autonomous Driving Technologies on Road Safety and Traffic Management

Research on Legal Risks Based on Autonomous Driving Technology

Research on Legal Risks Based on Autonomous Driving Technology

The Implementation and Potential Ramifications of Autonomous Driving Technology in The Realm of Freight Transportation and Logistics.

This paper aims to explore the application and potential impact of autonomous driving technology in the field of freight and logistics. First, the development of autonomous driving technology and its application in freight and logistics, including autonomous trucks, drones and drone delivery, as well as automated warehousing and sorting systems, are introduced. Then, the potential impacts of autonomous driving technology, such as improved efficiency, cost reduction, enhanced safety, and reduced environmental impact, are analyzed. The challenges faced by the application of autonomous driving technology, such as technological challenges, legal and ethical issues, and their impact on training and employment, are discussed. Finally, the potential advantages and strategies for addressing the application of autonomous driving technology in the field of freight and logistics are summarized, emphasizing the need to address ethical and legal issues in order to achieve sustainable and reasonable development.

The Development and Prospects of Autonomous Driving Technology

Autonomous driving is a topic of great interest for developers, researchers, and even automotive integrators and manufacturers [...]

Unveiling strategies in recent automotive history. Using patent citations for ambidexterity evidence

Through decarbonization of the world economy a normative imperative to the realization of a post-fossil age emerged. The global ecosystem is threatened by the current world economic model and fundamental transformations are asked for in all economic sectors. For two decades now, the automotive industry is undergoing a permanent ambidextrous phase, after having been locked in technological routines for nearly a century. The omni-present electrification of the powertrain together with the technological convergence with connected-car and autonomous-driving technology are the key challenges. To process the pressure, new strategies are designed and implemented. Nevertheless, current studies, based on patent analysis show that classic powertrain technology still represents the dominant design. At the same time, patent analysis shows that competition between firms in the field of electric powertrain technology is fierce. We use patent citation analysis to improve our understanding of the underlying industrial learning processes and of their impacts. To analyze the change in the automotive industry and unveil actors’ strategies, we examine the three most essential differentiating features of an automobile: classic powertrain, electric powertrain and autonomous driving. We aim to analyze these main differentiators along three key questions: the geographic dimension, the positioning in the value chain, and the individual company perspective, by developing a new structuring logic– the ambidexterity matrix – and its dynamic representation along the ambidexterity path.

UDP-YOLO: High Efficiency and Real-Time Performance of Autonomous Driving Technology

UDP-YOLO: High Efficiency and Real-Time Performance of Autonomous Driving Technology

Autonomous Vehicles for Enhancing Expressway Capacity: A Dynamic Perspective

With rapidly developing communication and autonomous-driving technology, traffic flow on road networks will change from homogeneous human-driven vehicle (HDV) traffic flow to heterogeneous mixed traffic flow (MTF) comprising HDVs, autonomous vehicles (AVs), and connective-and-autonomous vehicles (CAVs). To understand the changes in the MTF of transportation engineering, we investigated the reserved capacity (RC) and right-of-way (ROW) reallocation policy that should be utilized under MTF scenarios. We established an MTF-based theoretical model to calculate the expressway segment capacity, theoretically analyzed the influence of the market penetration rate (MPR) on capacity and validated the model through numerical analysis. The results showed that the MPR of AVs and CAVs can enhance the MTF RC that is within 0–200% and that the platooning rate of CAVs positively influences the MTF RC. CAV popularization does not necessarily lead to a rapid increase in the transportation system efficiency when the MPR is <40% but significantly improves the efficiency of existing urban transportation facilities. When the MPR is >40%, the greatest enhancement is 4800 pcu/h/lane in terms of RC. A ROW reallocation policy that equips CAV-dedicated lanes according to the MPR of AVs and CAVs can enhance the capacity of expressway systems by 500 pcu/h/lane in terms of RC.

IMPLEMENTASI DEEP LEARNING PADA SIMULASI AUTONOMOUS DRIVE MENGGUNAKAN AIRSIM

Autonomous Driving is one of the technologies available in Artificial Intelligence. This technology aims to facilitate human work related to driving. The application of this technology can be done by using one of the main capabilities found in Artificial Intelligence, namely Machine Learning. By using several methods found in Machine Learning, Autonomous Driving Technology can be formed and developed. This paper will discuss how to make Autonomous Driving technology using available methods and show the results obtained from using these methods.

How to Improve the Acceptance of Autonomous Driving Technology: Effective Elements Identified on the Basis of the Kano Model

Innovative sociotechnical change is forthcoming because of autonomous driving; however, only a few studies have focused on the acceptance of this technology, which is not up to social expectation. In this study, we present and validate a research framework on the basis of the Kano model to identify the effective acceptance elements for autonomous driving technology. By collecting and analyzing the survey data of 187 people, it was confirmed that the elements of acceptance for autonomous driving technology can be classified according to the Kano attributes. This means that these acceptance elements should be resolved with priority in order to secure the acceptance. Legal policies and ethical guidelines are identified as top priorities for ensuring the acceptance of autonomous driving. Traffic congestion, situational awareness, malfunction prevention, and fatigue/stress relief must be addressed as utmost priorities. The framework and results from this study can be used to establish efficient strategies for developing autonomous driving technologies according to the user requirement levels.

Practice of Cross-Departmental Competition Using AI Autonomous Driving Technology Education Teaching Material

It is important to further improve autonomous driving technology from the viewpoint of not only reducing vehicle accidents, but also reducing the burden on drivers, improving public transportation, and solving the labor shortage at logistics sites. Therefore, there is an urgent need to train engineers who understand autonomous driving technology and learn how to use it. Engineers involved in autonomous driving are required to have not only vehicle dynamics and control, but also expertise in information systems, as well as knowledge and experience in autonomous driving using AI. The authors have developed educational materials for AI autonomous driving technology, and practiced using the teaching materials according to classroom lectures on vehicle motion and AI. We aimed to develop human resources that contribute to the new development of the industry by holding competitions that compete for comprehensive performance of vehicle motion, control, AI, etc. using these AI-equipped vehicle learning materials. Information system department and mechanical system department participated in this trial of new utilization. This paper describes the practice of an AI automated driving competition with the participation of students from multiple departments as a cross-disciplinary competition and its effects.

Research on Autonomous Driving Technology for a Robot Vehicle in Mountainous Farmland Using the Quasi-Zenith Satellite System

Research on Autonomous Driving Technology for a Robot Vehicle in Mountainous Farmland Using the Quasi-Zenith Satellite System

Development of Teaching Materials KaitCV for Learning Autonomous Driving Technology and Practice of Class

Educating engineers who can be involved in automobile development requires expertise in mechanical, electrical, and information systems. Until now, there has been specialized education in each field. However, there were few practical educational cases in which specialized fields were integrated into vehicles. In addition, there was no teaching material that could effectively and inexpensively teach each of “driving environment sensing,” “driving behavior generation,” and “vehicle motion control,” which are essential basic technologies for realizing autonomous driving. The purpose of this study is to develop “KaitCV”, an automatic driving learning support teaching material that uses simple and inexpensive teaching materials such as hobby cars, so that all students can practice the acquisition of automatic driving technology. In addition, I will explain that the educational practice was carried out using the developed teaching materials and that a high educational effect was obtained.

The Social Justice of Intelligent Transportation Systems: Deep Learning-based Autonomous Driving Technologies, Cooperative Navigation Algorithms, and Vehicle and Pedestrian Detection Tools

The Social Justice of Intelligent Transportation Systems: Deep Learning-based Autonomous Driving Technologies, Cooperative Navigation Algorithms, and Vehicle and Pedestrian Detection Tools

Analysis of the Requirements of the Persons with Disabilities Using Wheelchair for the Mobility Support Service of the Transportation Vulnerable by Lv.4+ Autonomous Driving Technology: Application of KANO Model

인간에게 있어서 이동의 자유 및 이동권은 자신의 기본권 실현에 있어 매우 중요하고, 특히 장애인뿐만 아니라 노인, 임산부 등 이동에 불편을 가지는 교통약자들에게 있어 이동권 보장에 대한 과제는 중요하게 인정되고 있다. 휠체어 이용 장애인에게 이동권 확보는 사회 구성원으로서의 삶을 가능하게 하는 필수적인 요소이다. 한편, 자율주행차량은 미래형 자동차로써 ‘이동’이라는 측면에 있어서 휠체어 이용 장애인에게 이동권의 자유를 기대할 수 있으나 자율주행차량의 광범위하고 보편적인 이용의 실현을 위한 시설 등이 구축되어 있지 않은 실정이고, 이에 대한 사회 전반의 인지 및 제도, 정책은 이렇다 할 변화가 없는 상황이다. 이에 본 연구는 휠체어 이용 장애인의 자율주행기반 미래 모빌리티 서비스에 대한 기능적 우선순위를 검토하기 위하여 KANO 모델 분석기법을 사용하고, 그 결과를 분석하였으며, 이를 통하여 휠체어 이용 장애인의 요구사항에 대한 기술적 선호도 우선순위를 확인할 수 있었다. KANO 모델을 적용한 결과 총 31개의 품질평가 항목요소 중 일원적 품질요소 15개 항목, 매력적 품질요소 13개 항목, 무관심 품질요소 2개 항목, 당연적 품질요소 1개 항목으로 도출되었으며 휠체어 이용 장애인의 요구사항 정의에 따른 PCSI를 기반한 우선순위 5가지는 ⑴ 문자로 안내 문자 수신 기능(이용일시, 목적지, 차량번호 등), ⑵ 앱에서 예약 취소 기능, ⑶ 차량에서 이용자 인식 기능(센서, 음성, 키패드, NFC 방식 등) 및 음성안내, ⑷ 차량에서 돌발상황 발생시 관제센터 연결 기능(음성인식 기반), ⑸ 앱에서 예약변경 기능(시간, 경로) 가능으로 확인되었다. 이에 본 연구는 Lv.4+ 자율주행기술을 적용한 교통약자 모빌리티 서비스 기술 개발에 있어 휠체어 이용 장애인의 기능적 요구사항을 확인하고 기능적 우선순위를 검토함으로써 향후 특별교통수단 서비스에 대한 자율주행기술 개발의 성공에 기여할 것으로 기대된다.

Low‐Speed Control Experiment of Motorcycles Using SPACAR Model

The main stream of development of autonomous driving technology (ADT) is for four‐wheel motor vehicles. ADT for motorcycles has received scant attention. The motorcycle stability tends to diminish when being driven at extremely low speed. This study addresses how a motorcycle should be stabilized under low‐speed driving. To obtain a linearized motorcycle model without skidding, we introduce a model based on SPACAR, a finite element method computation program. Moreover, velocity‐dependent gain‐scheduling linear quadratic regulator (LQR) is applied. The experimental results demonstrate stabilized driving responses at 1.5 km/h, which is slower than a person's typical walking speed. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Train here, drive there: ROS based end-to-end autonomous-driving pipeline validation in CARLA simulator using the NHTSA typology

Urban complex scenarios are the most challenging situations in the field of Autonomous Driving (AD). In that sense, an AD pipeline should be tested in countless environments and scenarios, escalating the cost and development time exponentially with a physical approach. In this paper we present a validation of our fully-autonomous driving architecture using the NHTSA (National Highway Traffic Safety Administration) protocol in the CARLA simulator, focusing on the analysis of our decision-making module, based on Hierarchical Interpreted Binary Petri Nets (HIBPN). First, the paper states the importance of using hyper-realistic simulators, as a preliminary help to real test, as well as an appropriate design of the traffic scenarios as the two current keys to build safe and robust AD technology. Second, our pipeline is introduced, which exploits the concepts of standard communication in robotics using the Robot Operating System (ROS) and the Docker approach to provide the system with isolation, flexibility and portability, describing the main modules and approaches to perform the navigation. Third, the CARLA simulator is described, outlining the steps carried out to merge our architecture with the simulator and the advantages to create ad-hoc driving scenarios for use cases validation instead of just modular evaluation. Finally, the architecture is validated using some challenging driving scenarios such as Pedestrian Crossing, Stop, Adaptive Cruise Control (ACC) and Unexpected Pedestrian. Some qualitative (video files: Simulation Use Cases) and quantitative (linear velocity and trajectory splitted in the corresponding HIBPN states) results are presented for each use case, as well as an analysis of the temporal graphs associated to the Vulnerable Road Users (VRU) cases, validating our architecture in simulation as a preliminary stage before implementing it in our real autonomous electric car.

Latent heterogeneity in autonomous driving preferences and in-vehicle activities by travel distance

Autonomous driving technologies (ADTs) are transformative because they are expected to assume the task of driving. Since travel distance is closely related to the burden of driving, it is expected to affect the ADT preference; however, this effect has not been investigated in the transportation literature. Therefore, this study is designed to investigate the ADT preference and heterogeneity with respect to different travel distances. Hypothetical choice situations were designed to investigate people's ADT preferences over human driving for varying travel distances. Using the stated preference data collected via the experiments, four latent class models were estimated for heterogeneity across classes and travel distances. The estimation results show that three classes, we labeled as competitive, autonomous vehicle oriented, human-driven vehicle oriented, are revealed by the ADT preference, regardless of the travel distance. In addition, in-vehicle activities in hypothetical autonomous driving situations were observed across all the classes and travel distances.

Technological Cooperation Network Analysis through Patent Analysis of Autonomous Driving Technology

Technological Cooperation Network Analysis through Patent Analysis of Autonomous Driving Technology